Continue.dev | Northern Inference docs

Use Northern Inference in Continue for VS Code and JetBrains, with exact Canadian-resident routes and custody records for public-sector and regulated teams.

Northern Inference is a sovereign Canadian AI API for government, defence, health and regulated teams, including organizations under the Controlled Goods Program. Every route carries PIPEDA-aligned Canadian data residency, an exact path to the latest frontier and open-weight models, and a per-request chain-of-custody record.

Before you start

Create an API key. In the portal, open Keys and click Create Key. Your key starts with ni_live_.
Add credit. New accounts start with a balance of $0, and every request is refused until you add credit. Open Billing and click Buy credits.
Pick a model. Northern Inference model names end in a tier tag, for example claude-sonnet-4-6-t4. See them all on the Models page.

Set up Continue

1. Open Continue's config file. In the Continue panel in VS Code or JetBrains, open the configs menu and click the cog next to Local Config. The file is ~/.continue/config.yaml on Mac and Linux, and C:\Users\you\.continue\config.yaml on Windows.

2. Replace its contents with this, with your key in both places:

name: Northern Inference
version: 1.0.0
schema: v1

models:
  - name: Claude Sonnet 4.6 (Northern Inference)
    provider: openai
    model: claude-sonnet-4-6-t4
    apiBase: https://northerninference.ca/v1
    apiKey: ni_live_YOUR_KEY_HERE
    roles:
      - chat
      - edit
      - apply

  - name: Claude Haiku 4.5 (autocomplete)
    provider: openai
    model: claude-haiku-4-5-20251001-t4
    apiBase: https://northerninference.ca/v1
    apiKey: ni_live_YOUR_KEY_HERE
    roles:
      - autocomplete

If you already have models in this file, add these two entries under models: instead of replacing the file.

3. Send a message. Save the file, pick Claude Sonnet 4.6 (Northern Inference) in the Continue chat and send a message. It appears in the portal under Usage within a few seconds.

What the two models do

The first model answers in chat and makes edits.
The second model fills in code as you type (the autocomplete role). Autocomplete sends many small requests, so it uses a small, cheap model. Remove that entry if you do not want autocomplete.

provider: openai tells Continue to talk to Northern Inference as an OpenAI-compatible service. model must be an exact name from the Models page. The name is only the label Continue shows you.

If a model name is not recognized

Northern Inference answers with HTTP 404 and Model 'X' is not a route this key can call. It never swaps in a different model. Use a name from the Models page, or type ni-models as a chat message to list the models your key can call.

Troubleshooting

What you see	What to do
Continue shows a config error	Check that the file keeps `name`, `version` and `schema` at the top and that the indentation matches the example.
401	The key is wrong or was revoked. Copy it again from the portal under Keys.
402 `Insufficient credits. Add credits in the portal under Billing (https://northerninference.ca/portal/?page=billing) to continue.`	Add credit in the portal under Billing.
404 `Model 'X' is not a route this key can call.`	Use a name from the Models page, or type `ni-models`.

Spend limits

Autocomplete can add up. To cap it, create a separate key for the autocomplete model in the portal under Keys, with a Max spend per day limit, and use that key in the autocomplete entry.